metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-small
tags:
- transcribe
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
model-index:
- name: ./whisper-small-test230724_1000
results: []
./whisper-small-test230724_1000
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7148
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40
- training_steps: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9199 | 0.5263 | 10 | 2.5824 |
| 2.043 | 1.0526 | 20 | 1.8251 |
| 1.1702 | 1.5789 | 30 | 0.9278 |
| 0.7203 | 2.1053 | 40 | 0.7148 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1